Mathematics is regarded as the Queen of all sciences. Mathematics help us in abstract reasoning. It's the study of all possible patterns, said the British Mathematician W W Sawyer. Environmental regularities makes it possible to generalize from previous experience. Exploiting them is focus of much of our work on neural nets. Artificial Neural Networks (ANNs) are a revolutionary addition in our skill-set for complex problem-solving. They provide an amazing paradigm in computing. ANNs are systems for statistical pattern recognition. A great deal of research is taking place in the design and implementation of ANNs worldwide. This ranges from basic research into new and more efficient learning algorithms, to networks which can respond to temporally varying patterns, to techniques for implementing neural networks directly in silicon. Existing neural network systems are generally software models for solving static problems on PCs. There is also particular interest in sensory and sensing
applications: nets which learn to interpret real-world sensors and learn about their environment. Neural networks are applicable in virtually every situation in which a relationship between the predictor variables (independents, inputs) and predicted variables (dependents, outputs) exists, even when that relationship is very complex and not easy to articulate in the usual terms of "correlations" or "differences between groups." A few representative examples of problems to which neural network analysis has been applied successfully are detection of medical phenomena, stock market prediction, forecast of floods, credit card use and counterfeit checking, monitoring condition of machinery, pattern recognition, signal detection, speech recognition, and image processing. Many people consider ANNs as a black-box system in which data could be poured and a solution would eventually emerge. That’s a misconception. The purpose of addressing this area is that the neural networks technology is presently under-utilized despite being so promising. The reasons include: ANNs inability to justify answers; thereby difficulty of acceptance by those who do not understand it. Development process is mysterious - still a black-art. Developer’s inability to manually modify the system or introduce a certain behavior. Lack of understanding for tactful data-preparation before training No exact solution – difficulties in achieving good generalization Still, the ANNs technology is promising and the performance speaks. Researchers are taking interest in resolving the above issues and this platform provides an excellent opportunity to share our thoughts and experiences. For technical and organizational support, I wish to thank Institute for the Systems and Technologies of Information, Control, and Communication (INSTICC), Setúbal, Portugal. Finally, I wish to warmly thank Prof. Joaquim Filipe, who with skill and patience acted as Chair of the International Conference on Informatics in Control, Automation and Robotics (ICINCO 2004). I would like to mention Prof. Paula Miranda (Organizing Committee) and Ms Marina Carvalho (ICINCO Secretariat) for their valued and long-term coordination in preparation and management. Among many people engaged in making this Workshop a successful event, I also would like to give special thanks to our keynote speaker, Dr. Abdul Ahad Siddiqi, Dean Karachi Institute of Information Technology, Karachi, Pakistan and the Chairman CISE & Dean, Dr. Shahid Hafeez Mirza, NED University of Engineering & Technology, Karachi, Pakistan and all the participants of the workshop.
Vol. 1 - 972-8865-14-7